Deep Learning Neural Networks for Online Monitoring of the Combustion Process From Flame Colour in Thermal Power Plants

Author:

Kesavan Sujatha1,Sivanand R. 1,Rengammal Sankari B. 1,Latha B. 1,Tamilselvi C. 1,Krishnaveni S. 1

Affiliation:

1. Dr. MGR Educational and Research Institute, India

Abstract

The combustion quality determination in power station boilers is of great importance to avoid air pollution. Complete combustion minimizes the exit of NOx, SOx, CO, and CO2 emissions, also ensuring the consistency in load generation in thermal power plants. This chapter proposes a novel hybrid algorithm, called black widow optimization algorithm with mayfly optimization algorithm (BWO-MA), for solving global optimization problems. In this chapter, an effort is made to develop BWO-MA with artificial neural networks (ANN)-based diagnostic model for onset detection of incomplete combustion. Comparison has been done with existing machine learning methods with the proposed BWO-MA-based ANN architecture to accommodate the greater performance. The comprehensive analysis showed that the proposed achieved splendid state-of-the-art performance.

Publisher

IGI Global

Reference12 articles.

1. Abdul Rahman, M.G., Gibbins, J.R, & Forrest, A.K. (2004). Combustion in Power Station Boilers –Advanced Monitoring Using Imaging. Imperial College of Science, Technology, and Medicine.

2. Gilabert, Lu, & Yan. (2005). Three dimensional visualisation and reconstruction of the luminosity distribution of a flame using digital imaging. Techniques, Sensors & Their Applications, 167–171.

3. Han, Zhang, Zhen, & Wang. (2006). Boiler Flame Image Classification Based on Hidden Markov Model. IEEE ISIE, 9-12.

4. Advanced Spatial Data Analysis and Modelling with Support Vector Machines;M.Kanevski;International Journal of Fuzzy Systems,2002

5. Lu & Yan. (2009). Advanced Monitoring and Characterization of combustion flames. 20th annual meeting and meeting of the Advanced Power Generation Division, 1-25.

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3